Publication Search

This study proposes a computer vision-based system for automatically verifying the use of Personal Protective Equipment (PPE) in industrial environments. The system integrates the YOLOv8 object detection model, OpenCV for image processing, and a State Machine mechanism to manage the verification workflow. The verification process begins with employee identification through ID card scanning, followed by real-time detection of the head, safety helmet, and face mask using a camera, before generating a final PASS or FAIL decision. System evaluation was conducted using 250 testing scenarios to assess both model and system performance. The results show that the YOLOv8 model achieved an mAP@50 of 93.9%, while the overall verification system obtained 98.4% accuracy, 98.4% precision, 100% recall, and a 99.2% F1-score. The implementation of the State Machine contributed to a more stable and consistent verification process by ensuring that each inspection stage was executed in the correct sequence. These findings demonstrate that the proposed system can effectively support automated PPE compliance monitoring and has the potential to enhance occupational safety management in industrial workplaces. 

The development of Artificial Intelligence (AI) has driven significant transformation in hospital management, particularly in operational efficiency, service quality, and patient safety. This study aims to analyze the implementation of AI in hospital management based on recent scientific evidence from 2020 to 2026. The method used was a systematic review guided by the PRISMA 2020 framework. Literature was retrieved from PubMed, ScienceDirect, SpringerLink, Google Scholar, and ProQuest. From 360 identified articles, a stepwise selection process was conducted, resulting in 15 articles that met the inclusion criteria. The findings indicate that AI contributes to improved operational efficiency through patient flow optimization, operating room management, workforce scheduling, and electronic medical record management. AI also enhances service quality through predictive data analytics and supports patient safety through risk detection and early warning systems. In conclusion, AI has strong strategic potential to support modern hospital management. However, its implementation still faces several challenges, including human resource readiness, data security, algorithmic bias, system interoperability, and investment requirements. Therefore, AI implementation should be carried out in a planned, ethical manner and evaluated from a health economics perspective.

Anxiety during pregnancy is one of the most common psychological problems experienced by pregnant women, particularly during the third trimester when they face childbirth preparation as well as various physical and emotional changes. If not properly managed, anxiety may adversely affect both maternal and fetal health. This study aimed to describe the level of anxiety among third-trimester pregnant women at Mlati II Public Health Center in 2026. This research employed a descriptive quantitative design with a cross-sectional approach. The study involved 40 third-trimester pregnant women selected using a total sampling technique. Data were collected using the Hamilton Anxiety Rating Scale (HARS) questionnaire and analyzed through univariate analysis in the form of frequency and percentage distributions. The results showed that most respondents were of healthy reproductive age (20–35 years) (92.5%), primigravida (67.5%), had a secondary level of education (70%), and were unemployed (70%). The respondents' anxiety levels were categorized as no anxiety (47.5%), mild anxiety (47.5%), and moderate anxiety (5%), while no cases of severe anxiety or panic were identified. The most dominant anxiety indicators were anxious feelings, tension, respiratory symptoms, and sleep disturbances. These findings indicate that some third-trimester pregnant women still experience anxiety, highlighting the need for early detection, health education, and psychological support through antenatal care services to promote maternal mental well-being during pregnancy.

Background: Stunting remains one of the public health problems that requires early prevention through health education and growth monitoring in children under five years old. Lack of parental knowledge regarding balanced nutrition, child feeding practices, hygiene, and routine physical examination can increase the risk of growth disorders in toddlers. Purpose: Physical examination in toddlers is important to identify early signs of growth and developmental problems, including body weight, height or length, nutritional status, and general physical condition. Method: This community service activity was conducted face-to-face using health education, discussion, and direct physical examination methods. The stages of activity included preparation, delivery of educational materials about stunting, physical examination of toddlers, recording the results, and providing simple counseling to parents. Results: The activity showed that mothers were enthusiastic in participating in counseling and toddler physical examination. Before the education was given, several mothers still had limited understanding about the causes, impacts, and prevention of stunting. After the activity, mothers began to understand the importance of balanced nutrition, routine weighing, height measurement, immunization, hygiene, and regular visits to posyandu or health facilities. Conclusion: Education about stunting and physical examination of toddlers can increase parental awareness regarding early prevention of growth disorders. This activity is useful in encouraging families to monitor toddler growth regularly and implement healthy childcare practices.

Urban plant care is increasingly important for sustainable living, but many users face inconsistent watering, insufficient care knowledge, unsuitable plant selection and delayed disease recognition. This study presents Easy Grow Plants, an integrated web and Internet of Things (IoT) ecosystem that connects plant care guidance, soil-moisture monitoring, automated watering, plant recommendation, image-based plant health assistance, marketplace functions, community interaction and plant exchange. The prototype was implemented using a React frontend, Django REST backend, SQLite database and an Arduino UNO R4 WiFi smart pot with a soil moisture sensor, relay module and DC water pump. Functional, interface, API, IoT connectivity, sensor calibration, watering control and LAN deployment tests were conducted. The results show that the core modules operated together as an integrated academic prototype. The system demonstrates a practical foundation for smart urban gardening, although cloud deployment, multi-device testing and stronger AI validation remain future improvements

This research is motivated by the problems in manual attendance systems at schools, which remain vulnerable to fraud, time-consuming, and inefficient. The expected solution is to develop an automated attendance system based on face recognition that can operate in realtime with high accuracy. The research object is vocational high school students, with the applied method implementing the YOLO v10 algorithm for face detection, followed by the face_recognition library for identification. The instruments used include an Imou CCTV camera as the input device, a mid-range laptop as the hardware platform, and Python with SQLite as the software environment for data processing and attendance storage. The results show that the developed system achieved an average face detection accuracy of 96% under normal lighting and 91% under low lighting, with an average processing speed of 27 FPS. The implementation of an anti-duplication feature also ensured data validity by allowing each student to be recorded only once per day. In conclusion, the use of YOLO v10 in face-based attendance proved to be effective, efficient, and capable of reducing fraud. The implication of this study is that the system can be applied in both Islamic boarding schools and general schools as a modernization of attendance systems, with a recommendation for further development through web-based application and cloud database integration.

This study discusses a student concentration detection system using Convolutional Neural Network (CNN) with the MobileNetV2 architecture. The dataset was adapted from Classroom Student Behaviors and mapped into four concentration categories: highly focused, focused, less focused, and unfocused. The system was tested with a 720p webcam and produced real-time detection data. The evaluation results show an overall accuracy of 75.85%, with the highest precision achieved in the focused class (0.9859) and the highest recall in the highly focused (0.9739) and unfocused (0.9811) classes. The confusion matrix indicates that the focused class was detected most consistently, while highly focused and unfocused classes were often misclassified as focused, resulting in lower precision. In real-time testing, the system operated at an average of 7 FPS and worked optimally when students faced the camera directly with sufficient lighting, but its performance decreased significantly at face angles greater than 45°. User evaluation shows that 75% of students rated the detection results as accurate/very accurate with an average satisfaction score of 3.6 out of 5, and 75% felt assisted in recognizing their concentration level. From the teachers’ perspective, most stated that the results were consistent with classroom observations, and all expressed willingness to reuse the system.

Along with the times, computer technology is developing very rapidly. The increasingly rapid development of computer technology means that everyone is required to utilize computer technology in their daily lives. Utilization of technology is one of the implementation roles of scientific disciplines. The reason behind the formation of this research is so that in the future it will become a fun learning concept in the introduction of objects and shapes in children and the motor development of children. children are usually more interested in seeing pictorial text, or pictures that contain lots of color. The Viola Jones method itself was chosen as the research completion algorithm. The Viola Jones method is usually used as a method in research that discusses the detection of objects, faces and others. The Viola Jones method was chosen because it has a high level of accuracy that can reach 100% probability.

The implementation of smoking prohibition policies in Islamic boarding schools continues to depend largely on manual monitoring methods, which often face challenges related to consistency and supervision range. This study aims to design an Internet of Things (IoT)-based cigarette smoke detection system as an alternative monitoring approach that is more effective, measurable, and sustainable. The system design combines an MQ-2 gas sensor with a NodeMCU ESP8266 microcontroller programmed through the Arduino IDE platform. When smoke levels detected by the sensor exceed the predetermined limit, the system automatically triggers a buzzer and LED as warning indicators while simultaneously sending monitoring data to cloud-based platforms such as Firebase or ThingSpeak for real-time observation through web interfaces. The research outputs include a comprehensive system design consisting of system architecture, electronic circuit schematics, flowcharts, and pseudocode that are systematically arranged to support future prototype development and implementation. Through this design, the proposed system is expected to provide an initial technological solution that can enhance the effectiveness of monitoring and enforcing smoke-free regulations within Islamic boarding school environments.

Indonesia's maritime security faces increasingly complex challenges due to the rise of hybrid threats that combine traditional and non-traditional elements. One of the main threats is the shadow fleet, operating covertly with unregistered ships, evading detection, and exploiting weaknesses in maritime surveillance to engage in illegal activities such as smuggling, illegal transshipment, and unlawful exploitation of natural resources. This phenomenon exacerbates Indonesia's maritime security situation, particularly in strategic areas like the Natuna Sea and the Sunda Strait, which are vulnerable to geopolitical conflicts and overlapping territorial claims. Additionally, transnational crimes such as piracy, drug trafficking, and human trafficking further undermine security in Indonesian waters. To address these threats, Indonesia needs to strengthen its maritime surveillance capacity by adopting advanced technologies such as early detection sistems and the Automatic Identification Sistem (AIS), as well as enhancing coordination between maritime agencies like Bakamla and the Indonesian Navy (TNI AL) to improve responses to harder-to-detect threats. Moreover, international cooperation with neighboring countries and regional maritime organizations like ASEAN must be bolstered to tackle cross-border threats. Strengthening surveillance, modernizing technology, and fostering more integrative maritime diplomacy will be crucial in safeguarding Indonesia's maritime sovereignty and ensuring the stability of this increasingly strategic maritime region.

Background: Pregnancy is a crucial period that requires special attention to the mother's physiological and psychological aspects. Many pregnant women experience poorly understood physical and emotional changes, lack of early detection of high-risk pregnancies, and lack of knowledge about a healthy lifestyle during pregnancy, including physical activity and balanced nutrition. The main problems faced are pregnant women's lack of understanding of normal physiological and psychological changes during pregnancy, lack of knowledge about danger signs and how to detect high-risk pregnancies, low participation of pregnant women in physical activities such as prenatal exercise, lack of knowledge regarding balanced nutrition for pregnant women, and limited comprehensive health education facilities in the community. Objective: This community service activity aims to improve the health of pregnant women by strengthening promotive and preventive pregnancy classes. Methods: This community service activity included screening for high-risk pregnancies, providing materials on physiological and psychological changes in pregnancy, maternal nutrition, and early detection of complications in high-risk pregnancies. A demonstration of prenatal exercise practices was also conducted at the Pondokgebangsari Village Hall, Kuwarasan District, Kebumen Regency. The training, conducted in February 2026, involved 15 pregnant women in their first, second, and third trimesters. Results: This activity demonstrated an increase in mothers' knowledge about physiological, psychological changes, and pregnancy nutrition after education, with 8 receiving good and 7 receiving adequate education. Education on Early Detection and Danger Signs of High-Risk Pregnancy also increased, with 9 receiving good and 6 receiving adequate education. Thus, families are aware of the importance of attending pregnancy classes and see them as essential for a healthy pregnancy. Conclusion: Community service programs to strengthen pregnancy classes through education, high-risk screening, and nutrition counseling support efforts to improve maternal and infant health, and are an investment in the future.

People with visual impairment face barriers in cash transactions, particularly in identifying banknote denominations and verifying authenticity, which can reduce independence and increase vulnerability to fraud. This issue is also closely linked to the financial inclusion agenda, as access to reliable information on the value and authenticity of cash is a prerequisite for safe transactions among vulnerable groups. This community service program aimed to improve users’ competence through individualized, home-visit–based education and mentoring on an optical–UV sensor–based banknote denomination and authenticity detector with audio feedback. The program was implemented in collaboration with the Kebumen branches of PERTUNI and ITMI from October to December 2025. The intervention stages included an initial needs assessment, structured training using a concise module, hands-on practice through transaction scenarios, and follow-up mentoring. Evaluation employed a pre–post knowledge test, a practical performance checklist, and a usability questionnaire. Results indicated that the mean knowledge score increased from 55.1 to 80.7, and the success rate of denomination identification improved from 60.7% to 90.0%. This approach is relevant as an individualized mentoring model for blind communities when group-based training is difficult to implement.

Adolescent mental health is an important aspect in human resource development because it affects learning ability, social relationships, and readiness to face adult life. Adolescence, especially at the junior high school level, is a transitional period that is prone to mental and emotional disorders due to biological, psychological, and social changes that occur simultaneously. This study aims to describe the mental health condition of adolescents using the Self Reporting Questionnaire (SRQ-20) instrument in students of SMPN 3 Ubud, Gianyar Regency. The study used a descriptive design with a cross sectional approach. The sampling technique was carried out in total sampling with a total of 117 students. The research instrument is in the form of an SRQ-20 questionnaire that has been proven to be valid and reliable. Data analysis was carried out descriptively to describe the distribution of symptoms and mental health categories of respondents. The results showed that most students were in the category of good mental health, although there were still a number of students with poor conditions. The most common symptoms are easy to feel tired and difficulty in making decisions. Based on the characteristics of respondents, students aged 13–15 years are more likely to experience poor mental health conditions than 11-13 years old, and the proportion of female students is higher than men in experiencing symptoms of mental emotional disorders. These findings affirm the importance of early detection of adolescent mental health in schools as the basis for promotive and preventive interventions, through optimizing the role of counseling guidance and creating a supportive school environment.

The governance of village funds represents a critical dimension of decentralized public financial management, particularly in remote and capacity-constrained regions where oversight mechanisms face structural limitations. This literature review examines the role of Risk-Based Internal Audit (RBIA) as a strategic instrument for strengthening the supervision of village fund management through risk mapping, early warning mechanisms, and fraud prevention. Adopting a state-of-the-art literature review design, the study synthesizes peer-reviewed journal articles, conference proceedings, and authoritative institutional reports published primarily within the last five years. The review integrates the analytical lenses of RBIA as articulated in the International Professional Practices Framework, Enterprise Risk Management (ERM) based on ISO 31000 and COSO ERM, the COSO Internal Control–Integrated Framework, and the Fraud Triangle and Fraud Diamond theories. Thematic synthesis reveals that effective village fund oversight depends on the systematic identification and prioritization of risk, the alignment of audit planning with high-risk areas, and the integration of internal control and risk management processes into audit assurance. Furthermore, the literature highlights the growing relevance of early warning systems and audit analytics in enabling proactive detection of emerging risks and potential fraud, although their implementation in remote areas remains constrained by limited data quality, digital infrastructure, and administrative capacity. This review contributes theoretically by consolidating fragmented strands of audit, risk management, and fraud literature into an integrated conceptual framework tailored to village fund governance. Practically, it offers evidence-based insights for auditors, policymakers, and local governments seeking to enhance accountability and risk-responsive oversight in decentralized and remote public finance settings.

The development of deepfake technology, which utilises artificial intelligence to manipulate images, videos and sounds, has led to a serious threat of sextortion. In the Indonesian context, high internet penetration and low awareness of digital security increase the risk of this crime. This research analyses the legal consequences of the misuse of deepfake technology in sextortion based on the Electronic Information and Transaction Law (UU ITE). Using normative juridical methods and descriptive-qualitative analysis, this research examines the legal challenges faced in enforcing sanctions against this crime and provides recommendations to strengthen the legal framework in Indonesia. The results show that there are gaps in the legal framework that need to be addressed, as well as the importance of education and capacity building of law enforcement in dealing with cybercrime. In addition, the development of more sophisticated deepfake detection technology is expected to be a solution in tackling this abuse in the future.

This study investigates the adoption of adaptive DevOps practices in embedded systems used in safety-critical industrial applications. Traditional DevOps models, which are primarily designed for cloud-based systems, face significant challenges when applied to embedded platforms due to hardware constraints, real-time performance requirements, and stringent safety standards. The research focuses on developing a tailored DevOps framework that integrates continuous integration/continuous delivery (CI or CD) pipelines, automation, real-time monitoring, and safety assurance processes to enhance system reliability, performance, and compliance with regulatory standards. The study uses a case study methodology, involving embedded system teams across multiple industrial sectors, to assess the impact of these adapted DevOps practices on system stability and operational efficiency. Key findings show that the adoption of adaptive DevOps practices led to significant improvements in system reliability, performance, and deployment stability. Continuous feedback mechanisms allowed for early issue detection and faster resolution, leading to enhanced system uptime and responsiveness. Additionally, the integration of safety assurance into the DevOps pipeline ensured that safety-critical systems complied with required safety integrity levels and certification standards. The study further explores the integration of DevOps with embedded safety-critical systems, highlighting the benefits of cross-domain collaboration, enhanced communication, and the ability to address the unique challenges of these platforms. The research also underscores the limitations of conventional DevOps models in embedded systems and presents practical implications for the wider adoption of DevOps in safety-critical industrial applications. Future research is recommended to refine DevOps frameworks for embedded systems, integrating emerging technologies like the Industrial Internet of Things (IIoT) and Digital Twins to further optimize performance, security, and predictive maintenance.

Distributed software systems face significant challenges related to data quality due to their complex, decentralized architecture. These systems often involve multiple nodes responsible for processing and storing data, making it difficult to maintain consistency and ensure accurate data across the entire network. In particular, issues like data inconsistency, latency, and data fragmentation are prevalent in distributed environments. To address these challenges, this study proposes an integrated data quality governance strategy that combines real time monitoring and automated anomaly detection using machine learning models. The proposed strategy aims to improve data consistency, enhance anomaly detection capabilities, and reduce the need for manual intervention, ultimately improving overall data governance in distributed systems. Real time monitoring ensures immediate identification of data issues as they occur, while machine learning models, such as autoencoders and Isolation Forests, automate the detection of anomalies based on high reconstruction errors and data isolation techniques. The study evaluates the proposed strategy through real-world distributed system scenarios, comparing its effectiveness to traditional approaches like periodic audits and manual validation. Results demonstrate that the integrated approach leads to faster anomaly detection, reduced data inconsistencies, and improved overall system performance. The use of advanced machine learning techniques and real time analytics significantly enhances the system's ability to maintain high data quality standards across multiple distributed nodes. This strategy has wide-ranging implications for industries that rely on distributed systems, such as finance, healthcare, and IoT, where data integrity is essential for operational success. Future research can focus on integrating more advanced machine learning techniques and optimizing the real time monitoring framework to handle larger and more complex systems.

The growing use of smartphones among adolescents carries a high risk of addiction, which can negatively impact physical, mental, and social well-being. To address this issue, a community service program was implemented to conduct early detection of gadget addiction among high school students and provide educational health media to raise knowledge and awareness about excessive smartphone use. The program involved 240 students of SMA Negeri 1 Tuntang and was conducted in three stages: screening, development of educational materials, and health counseling. Screening used the short version of the Smartphone Addiction Scale and revealed that 90% of students were classified as addicted. Prior to counseling, 81.25% of students had low levels of knowledge regarding healthy gadget use, which significantly improved after the intervention, with 83.4% achieving high knowledge levels. Health counseling proved crucial in enhancing students’ understanding and promoting responsible smartphone habits. The program highlights the importance of collaborative efforts by schools, parents, and students to limit smartphone use, encourage physical activity, and foster face-to-face social interactions to support adolescent well-being.

Early childhood development screening is an important effort to ensure optimal development during a child's golden age, which includes physical, motor, language, cognitive, and socio-emotional aspects. Early Childhood Education (PAUD) teachers play a key role in implementing early detection, given their intensive interaction with children during learning activities. However, early detection in PAUD institutions faces challenges such as limited teacher competencies, non-standardized screening instruments, and suboptimal cross-sector collaboration. This study aims to examine the role of teachers in early childhood development screening at RA Arrahmah using a qualitative approach and case study. Data were collected through observations, in-depth interviews, and documentation with the head of RA and class teachers during October-November. The results show that teachers have carried out early detection in an integrated manner through continuous observations. However, the use of standardized screening instruments has not been optimal and still relies on informal observations. Major challenges include limited training, individual observation time, and the lack of a structured early detection program. This study concludes that strengthening teacher competencies, integrating early detection into institutional policies, and enhancing collaboration with parents and healthcare professionals are necessary to optimize early childhood development screening sustainably.

Background: The development of industrial technology in the Industry 4.0 era has encouraged the implementation of intelligent monitoring systems to improve machine reliability and operational efficiency. However, machine fault diagnosis systems based on artificial intelligence often face limitations in terms of interpretability because the models used are complex and difficult to explain. Objective: This study aims to develop a deep learning-based industrial machine fault diagnosis system integrated with an Explainable Artificial Intelligence (XAI) approach to improve diagnostic accuracy while providing interpretable insights for users. Method: The research method involves collecting data from industrial machine sensors consisting of vibration signals, temperature measurements, and acoustic signals, followed by data preprocessing and feature extraction processes. The processed data are then used to train a deep learning-based diagnostic model, after which explainability methods such as SHAP or LIME are applied to analyze the contribution of each feature to the model’s prediction results. Model performance is evaluated using accuracy, precision, recall, and F1-score metrics. Results: The results indicate that the proposed deep learning model achieves better performance compared to conventional machine learning methods such as Support Vector Machine and Random Forest. Furthermore, the explainability analysis reveals that vibration amplitude, increases in machine component temperature, and anomalies in acoustic signals are the main factors influencing machine fault detection. Therefore, the proposed system not only improves the accuracy of machine fault diagnosis but also provides transparency in the decision-making process, thereby supporting the implementation of predictive maintenance in smart manufacturing environments.